© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11121
    Prev
    Next
    INDEX
    Explanations

    Yields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     उपचार
    0.39
    χή
    0.38
     extrémités
    0.37
    عين
    0.37
    글
    0.37
    قاء
    0.36
    ાલુ
    0.35
    ᄄ
    0.35
    敦煌
    0.35
    资源的
    0.34
    POSITIVE LOGITS
     Class
    0.40
    Class
    0.40
    class
    0.39
    channel
    0.37
    location
    0.36
    standard
    0.36
    object
    0.35
     standard
    0.34
    localization
    0.34
    fiber
    0.34
    Activations Density 0.003%

    No Known Activations